Stars
A simple, fast streaming JSON parser built on standards.
Parametric differentiable curves with PyTorch for KANs, continuous embeddings, or shape-restricted models
TypeScript-first fetch wrapper with configurable timeouts, retries, and circuit-breaker baked in.
Pure TypeScript media toolkit for reading, writing, and converting video and audio files, directly in the browser.
Voyager is an interactive RGBD video generation model conditioned on camera input, and supports real-time 3D reconstruction.
High-performance audio engine
[NeurIPS 2025] PyTorch implementation of [ThinkSound], a unified framework for generating audio from any modality, guided by Chain-of-Thought (CoT) reasoning.
A collection of basic effects, available as open-source (MIT) C++ classes.
A curated list of awesome deterministic simulation testing resources 😎
Kyutai's Speech-To-Text and Text-To-Speech models based on the Delayed Streams Modeling framework.
A projection-based framework for gradient-free and parallel learning
automatic audio labelling with laion-clap
Realtime softbody simulation in the browser with WebGPU
🪐 Markdown with superpowers — from ideas to papers, presentations and books.
Toolkit enabling the use of Zig code in JavaScript projects
Interactive visualizations of the geometric intuition behind diffusion models.
Unlimited text-to-speech in the Browser using Kokoro-JS, 100% local, 100% open source
DSPy: The framework for programming—not prompting—language models
Artificial Neural Engine Machine Learning Library
Lets make video diffusion practical!
Lightweight coding agent that runs in your terminal
Provide with pre-build flash-attention package wheels on Linux and Windows platforms using GitHub Actions
This project combines the power of Retrieval-Augmented Generation (RAG) with AssemblyAI's transcription capabilities, enabling you to interact with audio recordings as if they were conversational t…
💬 A proposal for a web API for prompting browser-provided language models